Marc Finzi
14 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (3) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (13)
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(3)
🏃
Academic Marathon
(5)
🌱
Topic Pioneer
💎
Century Club
(14)
🗃️
Keyword Collector
(71)
🔥
Unstoppable
(6)
Conferences
NIPS (9)
ICML (4)
ICLR (1)
Top co-authors
Keywords
neural network
(4)
convolutional neural network
(2)
generalization bound
(2)
representation learning
(2)
large language model
(2)
gaussian process
(2)
image classification
(1)
data augmentation
(1)
generative modeling
(1)
transfer learning
(1)
image generation
(1)
model architecture
(1)
trajectory prediction
(1)
group theory
(1)
neural network compression
(1)
automatic differentiation
(1)
constrained optimization
(1)
semi-supervised learning
(1)
efficient computing
(1)
neural network optimization
(1)
Papers
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
NIPS 2024
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
NIPS 2024
Diffusing Differentiable Representations
NIPS 2024
Large Language Models Are Zero-Shot Time Series Forecasters
NIPS 2023
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
NIPS 2023
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
NIPS 2022
SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes
ICML 2021
Residual Pathway Priors for Soft Equivariance Constraints
NIPS 2021
A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
ICML 2021
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
ICML 2020
Semi-Supervised Learning with Normalizing Flows
ICML 2020
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints
NIPS 2020
Learning Invariances in Neural Networks from Training Data
NIPS 2020
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
ICLR 2019